import pandas as pd
import numpy as np

df=pd.read_excel('survey_data2.xlsx')
df.head()

	Person	Age	Gender	State	Children	Salary	Opinion	Agree or Not	Unnamed: 8	Unnamed: 9
0	1	Middle-aged	2	Texas	2	63017	Strongly agree	1	NaN	NaN
1	2	Middle-aged	2	Virginia	3	100302	Strongly disagree	0	NaN	NaN
2	3	Middle-aged	2	California	0	144043	Strongly agree	1	NaN	NaN
3	4	Young	2	California	0	36025	Agree	1	NaN	NaN
4	5	Middle-aged	1	Texas	0	97543	Neutral	0	NaN	NaN

df=df[['Age','Gender', 'State', 'Children','Salary', 'Agree or Not']]
df.head()

	Age	Gender	State	Children	Salary	Agree or Not
0	Middle-aged	2	Texas	2	63017	1
1	Middle-aged	2	Virginia	3	100302	0
2	Middle-aged	2	California	0	144043	1
3	Young	2	California	0	36025	1
4	Middle-aged	1	Texas	0	97543	0

df = pd.concat([df,pd.get_dummies(df['Age'], prefix='_', drop_first=True)],axis=1)
df.drop(['Age'],axis=1, inplace=True)
df = pd.concat([df,pd.get_dummies(df['State'], prefix='State', drop_first=True)],axis=1)
df.drop(['State'],axis=1, inplace=True)
df['Gender']=df['Gender']-1
df.head()

	Gender	Children	Salary	Agree or Not	__Middle-aged	__Young	State_California	State_Florida	State_Illinois	State_Michigan	State_Minnesota	State_New York	State_Ohio	State_Texas	State_Virginia
0	1	2	63017	1	1	0	0	0	0	0	0	0	0	1	0
1	1	3	100302	0	1	0	0	0	0	0	0	0	0	0	1
2	1	0	144043	1	1	0	1	0	0	0	0	0	0	0	0
3	1	0	36025	1	0	1	1	0	0	0	0	0	0	0	0
4	0	0	97543	0	1	0	0	0	0	0	0	0	0	1	0

df1=df.copy()

df1['Gend_child']=df1['Gender']*df1['Children']
df1['log_Salary']=np.log(df1['Salary'])
df1['Salary_Sq'] = df1['Salary']**2
df1.head()

	Gender	Children	Salary	Agree or Not	__Middle-aged	__Young	State_California	State_Florida	State_Illinois	State_Michigan	State_Minnesota	State_New York	State_Ohio	State_Texas	State_Virginia	Gend_child	log_Salary	Salary_Sq
0	1	2	63017	1	1	0	0	0	0	0	0	0	0	1	0	2	11.051160	3971142289
1	1	3	100302	0	1	0	0	0	0	0	0	0	0	0	1	3	11.515941	10060491204
2	1	0	144043	1	1	0	1	0	0	0	0	0	0	0	0	0	11.877867	20748385849
3	1	0	36025	1	0	1	1	0	0	0	0	0	0	0	0	0	10.491968	1297800625
4	0	0	97543	0	1	0	0	0	0	0	0	0	0	1	0	0	11.488049	9514636849

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, confusion_matrix

df_copy = df.copy()
train_set = df_copy.sample(frac=0.80, random_state=0)
test_set = df_copy.drop(train_set.index)
train_set.head()

	Gender	Children	Salary	Agree or Not	__Middle-aged	__Young	State_California	State_Florida	State_Illinois	State_Michigan	State_Minnesota	State_New York	State_Ohio	State_Texas	State_Virginia
132	0	0	97814	0	1	0	0	0	0	0	0	1	0	0	0
309	0	2	69817	1	0	0	0	0	0	0	1	0	0	0	0
334	0	1	48225	0	0	1	0	0	0	1	0	0	0	0	0
196	0	0	37929	1	0	1	0	0	0	0	0	0	0	0	0
246	1	2	100062	1	1	0	0	0	0	0	0	1	0	0	0

test_set.head()

	Gender	Children	Salary	Agree or Not	__Middle-aged	__Young	State_California	State_Florida	State_Illinois	State_Michigan	State_Minnesota	State_New York	State_Ohio	State_Texas	State_Virginia
9	0	3	87457	1	1	0	0	0	1	0	0	0	0	0	0
25	1	2	148075	0	1	0	0	0	0	0	0	0	0	0	0
28	1	2	37963	0	0	1	1	0	0	0	0	0	0	0	0
31	1	2	49505	0	0	1	0	0	0	0	0	0	0	0	1
32	0	3	49723	0	0	1	1	0	0	0	0	0	0	0	0

test_set_labels = test_set.pop('Agree or Not')
train_set_labels = train_set.pop('Agree or Not')

model = LogisticRegression(solver = 'liblinear', random_state=0).fit(train_set,train_set_labels)

model.predict_proba(train_set)

array([[0.57614226, 0.42385774],
       [0.55455629, 0.44544371],
       [0.53776249, 0.46223751],
       [0.52972181, 0.47027819],
       [0.57786408, 0.42213592],
       [0.58483034, 0.41516966],
       [0.54040349, 0.45959651],
       [0.56540533, 0.43459467],
       [0.54585125, 0.45414875],
       [0.56552639, 0.43447361],
       [0.57141167, 0.42858833],
       [0.58043178, 0.41956822],
       [0.60341186, 0.39658814],
       [0.57132021, 0.42867979],
       [0.5893605 , 0.4106395 ],
       [0.56271841, 0.43728159],
       [0.54686083, 0.45313917],
       [0.58593019, 0.41406981],
       [0.53682003, 0.46317997],
       [0.58387605, 0.41612395],
       [0.55934182, 0.44065818],
       [0.56596354, 0.43403646],
       [0.60158629, 0.39841371],
       [0.53495542, 0.46504458],
       [0.56675815, 0.43324185],
       [0.57687778, 0.42312222],
       [0.58254418, 0.41745582],
       [0.53062622, 0.46937378],
       [0.57134019, 0.42865981],
       [0.58651175, 0.41348825],
       [0.59304194, 0.40695806],
       [0.53621291, 0.46378709],
       [0.58500863, 0.41499137],
       [0.56894906, 0.43105094],
       [0.53557681, 0.46442319],
       [0.58003509, 0.41996491],
       [0.61174906, 0.38825094],
       [0.53621604, 0.46378396],
       [0.52205014, 0.47794986],
       [0.56006569, 0.43993431],
       [0.53389272, 0.46610728],
       [0.55964656, 0.44035344],
       [0.56382465, 0.43617535],
       [0.57804779, 0.42195221],
       [0.55750088, 0.44249912],
       [0.59881966, 0.40118034],
       [0.52868818, 0.47131182],
       [0.54712211, 0.45287789],
       [0.54476892, 0.45523108],
       [0.57767345, 0.42232655],
       [0.60171942, 0.39828058],
       [0.54722553, 0.45277447],
       [0.53017912, 0.46982088],
       [0.62305308, 0.37694692],
       [0.57347701, 0.42652299],
       [0.54738492, 0.45261508],
       [0.57612003, 0.42387997],
       [0.53834046, 0.46165954],
       [0.57617521, 0.42382479],
       [0.55885524, 0.44114476],
       [0.54325247, 0.45674753],
       [0.56596277, 0.43403723],
       [0.57593456, 0.42406544],
       [0.53486408, 0.46513592],
       [0.56685755, 0.43314245],
       [0.55072519, 0.44927481],
       [0.58975613, 0.41024387],
       [0.554095  , 0.445905  ],
       [0.58681995, 0.41318005],
       [0.51626174, 0.48373826],
       [0.57926587, 0.42073413],
       [0.55168859, 0.44831141],
       [0.59888525, 0.40111475],
       [0.55290141, 0.44709859],
       [0.60811903, 0.39188097],
       [0.53694097, 0.46305903],
       [0.55069801, 0.44930199],
       [0.55876395, 0.44123605],
       [0.56508529, 0.43491471],
       [0.52922144, 0.47077856],
       [0.56297708, 0.43702292],
       [0.57488956, 0.42511044],
       [0.54378892, 0.45621108],
       [0.55693567, 0.44306433],
       [0.56747848, 0.43252152],
       [0.54154045, 0.45845955],
       [0.55130514, 0.44869486],
       [0.57066218, 0.42933782],
       [0.54748988, 0.45251012],
       [0.57547923, 0.42452077],
       [0.5740764 , 0.4259236 ],
       [0.56565207, 0.43434793],
       [0.5575094 , 0.4424906 ],
       [0.56540147, 0.43459853],
       [0.58493092, 0.41506908],
       [0.56023501, 0.43976499],
       [0.57156076, 0.42843924],
       [0.53703538, 0.46296462],
       [0.55730036, 0.44269964],
       [0.53313748, 0.46686252],
       [0.54884153, 0.45115847],
       [0.52919486, 0.47080514],
       [0.57626563, 0.42373437],
       [0.53432768, 0.46567232],
       [0.55857902, 0.44142098],
       [0.529979  , 0.470021  ],
       [0.55834378, 0.44165622],
       [0.58424733, 0.41575267],
       [0.58434947, 0.41565053],
       [0.56500276, 0.43499724],
       [0.61437241, 0.38562759],
       [0.52985314, 0.47014686],
       [0.55631376, 0.44368624],
       [0.53562286, 0.46437714],
       [0.58531487, 0.41468513],
       [0.55123061, 0.44876939],
       [0.58565531, 0.41434469],
       [0.59512758, 0.40487242],
       [0.52897437, 0.47102563],
       [0.58303481, 0.41696519],
       [0.57151004, 0.42848996],
       [0.51812204, 0.48187796],
       [0.56767334, 0.43232666],
       [0.53191955, 0.46808045],
       [0.56154741, 0.43845259],
       [0.58967716, 0.41032284],
       [0.55032527, 0.44967473],
       [0.54265828, 0.45734172],
       [0.53834748, 0.46165252],
       [0.52865456, 0.47134544],
       [0.55657556, 0.44342444],
       [0.57812509, 0.42187491],
       [0.56669882, 0.43330118],
       [0.57114189, 0.42885811],
       [0.58617228, 0.41382772],
       [0.56909375, 0.43090625],
       [0.51622412, 0.48377588],
       [0.55949342, 0.44050658],
       [0.57116649, 0.42883351],
       [0.55159623, 0.44840377],
       [0.56405771, 0.43594229],
       [0.53598736, 0.46401264],
       [0.56372818, 0.43627182],
       [0.5689329 , 0.4310671 ],
       [0.55088513, 0.44911487],
       [0.56637823, 0.43362177],
       [0.57965664, 0.42034336],
       [0.56069963, 0.43930037],
       [0.58574897, 0.41425103],
       [0.55643304, 0.44356696],
       [0.59786259, 0.40213741],
       [0.55926061, 0.44073939],
       [0.56555184, 0.43444816],
       [0.57654607, 0.42345393],
       [0.53371935, 0.46628065],
       [0.56564822, 0.43435178],
       [0.53564862, 0.46435138],
       [0.58691505, 0.41308495],
       [0.60021733, 0.39978267],
       [0.55765958, 0.44234042],
       [0.56534364, 0.43465636],
       [0.56073905, 0.43926095],
       [0.56396511, 0.43603489],
       [0.57015927, 0.42984073],
       [0.54005819, 0.45994181],
       [0.55208905, 0.44791095],
       [0.54357015, 0.45642985],
       [0.56221101, 0.43778899],
       [0.56670498, 0.43329502],
       [0.56277941, 0.43722059],
       [0.59667672, 0.40332328],
       [0.55375459, 0.44624541],
       [0.55446559, 0.44553441],
       [0.55686907, 0.44313093],
       [0.58065263, 0.41934737],
       [0.55884828, 0.44115172],
       [0.61133978, 0.38866022],
       [0.59358789, 0.40641211],
       [0.5531605 , 0.4468395 ],
       [0.57149621, 0.42850379],
       [0.57898439, 0.42101561],
       [0.5556909 , 0.4443091 ],
       [0.53603809, 0.46396191],
       [0.53618092, 0.46381908],
       [0.573444  , 0.426556  ],
       [0.55645163, 0.44354837],
       [0.55971229, 0.44028771],
       [0.56652543, 0.43347457],
       [0.5394852 , 0.4605148 ],
       [0.53954913, 0.46045087],
       [0.54976451, 0.45023549],
       [0.53808854, 0.46191146],
       [0.53521773, 0.46478227],
       [0.54921061, 0.45078939],
       [0.61112203, 0.38887797],
       [0.60021808, 0.39978192],
       [0.56328435, 0.43671565],
       [0.57931788, 0.42068212],
       [0.53222036, 0.46777964],
       [0.58049368, 0.41950632],
       [0.55038662, 0.44961338],
       [0.5728513 , 0.4271487 ],
       [0.58553041, 0.41446959],
       [0.57028924, 0.42971076],
       [0.58489663, 0.41510337],
       [0.55885292, 0.44114708],
       [0.5778235 , 0.4221765 ],
       [0.53107874, 0.46892126],
       [0.56566518, 0.43433482],
       [0.55453149, 0.44546851],
       [0.55242815, 0.44757185],
       [0.57273304, 0.42726696],
       [0.56405076, 0.43594924],
       [0.58325833, 0.41674167],
       [0.54079083, 0.45920917],
       [0.54083292, 0.45916708],
       [0.57548843, 0.42451157],
       [0.57305555, 0.42694445],
       [0.55553361, 0.44446639],
       [0.56252226, 0.43747774],
       [0.53878655, 0.46121345],
       [0.55922889, 0.44077111],
       [0.56392266, 0.43607734],
       [0.55293244, 0.44706756],
       [0.58555935, 0.41444065],
       [0.53775313, 0.46224687],
       [0.52454739, 0.47545261],
       [0.53418712, 0.46581288],
       [0.56699161, 0.43300839],
       [0.55295184, 0.44704816],
       [0.56117959, 0.43882041],
       [0.56182091, 0.43817909],
       [0.56126382, 0.43873618],
       [0.53440107, 0.46559893],
       [0.61407943, 0.38592057],
       [0.55055358, 0.44944642],
       [0.60224049, 0.39775951],
       [0.57169985, 0.42830015],
       [0.57175287, 0.42824713],
       [0.59396107, 0.40603893],
       [0.56441033, 0.43558967],
       [0.54664542, 0.45335458],
       [0.58470766, 0.41529234],
       [0.56903603, 0.43096397],
       [0.55719584, 0.44280416],
       [0.56240332, 0.43759668],
       [0.58250908, 0.41749092],
       [0.53288595, 0.46711405],
       [0.55796611, 0.44203389],
       [0.57236285, 0.42763715],
       [0.59832576, 0.40167424],
       [0.58335901, 0.41664099],
       [0.5208567 , 0.4791433 ],
       [0.56050869, 0.43949131],
       [0.59263365, 0.40736635],
       [0.56333375, 0.43666625],
       [0.55569013, 0.44430987],
       [0.57031077, 0.42968923],
       [0.56133724, 0.43866276],
       [0.53415589, 0.46584411],
       [0.53998959, 0.46001041],
       [0.58053648, 0.41946352],
       [0.54174613, 0.45825387],
       [0.56489864, 0.43510136],
       [0.54124047, 0.45875953],
       [0.52823306, 0.47176694],
       [0.51855139, 0.48144861],
       [0.5852067 , 0.4147933 ],
       [0.56616781, 0.43383219],
       [0.55158924, 0.44841076],
       [0.55997058, 0.44002942],
       [0.56743843, 0.43256157],
       [0.55027013, 0.44972987],
       [0.54627831, 0.45372169],
       [0.53971518, 0.46028482],
       [0.55599925, 0.44400075],
       [0.56199781, 0.43800219],
       [0.56926227, 0.43073773],
       [0.57883062, 0.42116938],
       [0.55575986, 0.44424014],
       [0.57091743, 0.42908257],
       [0.57950983, 0.42049017],
       [0.60408229, 0.39591771],
       [0.57150159, 0.42849841],
       [0.58090019, 0.41909981],
       [0.54765236, 0.45234764],
       [0.53287736, 0.46712264],
       [0.56185181, 0.43814819],
       [0.55186555, 0.44813445],
       [0.52986643, 0.47013357],
       [0.5320305 , 0.4679695 ],
       [0.5806213 , 0.4193787 ],
       [0.53944777, 0.46055223],
       [0.52353454, 0.47646546],
       [0.53446979, 0.46553021],
       [0.57496165, 0.42503835],
       [0.56127696, 0.43872304],
       [0.57958783, 0.42041217],
       [0.548697  , 0.451303  ],
       [0.54927898, 0.45072102],
       [0.5451549 , 0.4548451 ],
       [0.52996102, 0.47003898],
       [0.56775421, 0.43224579],
       [0.56787974, 0.43212026],
       [0.57696587, 0.42303413],
       [0.60379705, 0.39620295],
       [0.5654755 , 0.4345245 ],
       [0.57356605, 0.42643395],
       [0.53269535, 0.46730465],
       [0.53890274, 0.46109726],
       [0.5642321 , 0.4357679 ],
       [0.54833562, 0.45166438],
       [0.55837783, 0.44162217],
       [0.52792336, 0.47207664],
       [0.58321866, 0.41678134],
       [0.57472236, 0.42527764],
       [0.61566602, 0.38433398],
       [0.54172354, 0.45827646],
       [0.53458613, 0.46541387]])

model.predict(train_set)

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], dtype=int64)

model.predict_proba(test_set)

array([[0.5681862 , 0.4318138 ],
       [0.6141248 , 0.3858752 ],
       [0.52974839, 0.47025161],
       [0.53876082, 0.46123918],
       [0.53893082, 0.46106918],
       [0.57041151, 0.42958849],
       [0.53753002, 0.46246998],
       [0.57213394, 0.42786606],
       [0.57271308, 0.42728692],
       [0.56414799, 0.43585201],
       [0.59842003, 0.40157997],
       [0.52680482, 0.47319518],
       [0.56234077, 0.43765923],
       [0.56277555, 0.43722445],
       [0.54249083, 0.45750917],
       [0.53113188, 0.46886812],
       [0.54684995, 0.45315005],
       [0.53778277, 0.46221723],
       [0.5677673 , 0.4322327 ],
       [0.57894537, 0.42105463],
       [0.61147622, 0.38852378],
       [0.5581356 , 0.4418644 ],
       [0.56175756, 0.43824244],
       [0.59836271, 0.40163729],
       [0.56545622, 0.43454378],
       [0.55440512, 0.44559488],
       [0.54287479, 0.45712521],
       [0.60223598, 0.39776402],
       [0.53849567, 0.46150433],
       [0.59607769, 0.40392231],
       [0.58637628, 0.41362372],
       [0.57209399, 0.42790601],
       [0.58146544, 0.41853456],
       [0.56576387, 0.43423613],
       [0.56182709, 0.43817291],
       [0.55546465, 0.44453535],
       [0.53668816, 0.46331184],
       [0.5327266 , 0.4672734 ],
       [0.56258481, 0.43741519],
       [0.5449339 , 0.4550661 ],
       [0.55125623, 0.44874377],
       [0.54852214, 0.45147786],
       [0.56771108, 0.43228892],
       [0.57456741, 0.42543259],
       [0.53460252, 0.46539748],
       [0.56018321, 0.43981679],
       [0.53688167, 0.46311833],
       [0.54161992, 0.45838008],
       [0.58375177, 0.41624823],
       [0.5543462 , 0.4456538 ],
       [0.52879922, 0.47120078],
       [0.55965971, 0.44034029],
       [0.5609601 , 0.4390399 ],
       [0.535263  , 0.464737  ],
       [0.59502852, 0.40497148],
       [0.55951353, 0.44048647],
       [0.56587257, 0.43412743],
       [0.55827878, 0.44172122],
       [0.54580146, 0.45419854],
       [0.56661097, 0.43338903],
       [0.53454865, 0.46545135],
       [0.53428785, 0.46571215],
       [0.56091373, 0.43908627],
       [0.57105272, 0.42894728],
       [0.555398  , 0.444602  ],
       [0.59007498, 0.40992502],
       [0.57462341, 0.42537659],
       [0.54071212, 0.45928788],
       [0.57373798, 0.42626202],
       [0.56697621, 0.43302379],
       [0.56142301, 0.43857699],
       [0.602596  , 0.397404  ],
       [0.56667031, 0.43332969],
       [0.55353978, 0.44646022],
       [0.56563511, 0.43436489],
       [0.56849185, 0.43150815],
       [0.54393061, 0.45606939],
       [0.5680299 , 0.4319701 ],
       [0.56263346, 0.43736654],
       [0.56620095, 0.43379905]])

model.predict(test_set)

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], dtype=int64)

model.score(train_set,train_set_labels)

0.5768025078369906

model.score(test_set,test_set_labels)

0.5875

confusion_matrix(train_set_labels,model.predict(train_set))

array([[184,   0],
       [135,   0]], dtype=int64)

confusion_matrix(test_set_labels,model.predict(test_set))

array([[47,  0],
       [33,  0]], dtype=int64)

import matplotlib.pyplot as plt

cm = confusion_matrix(test_set_labels, model.predict(test_set))

fig, ax = plt.subplots(figsize=(8, 8))
ax.imshow(cm)
ax.grid(False)
ax.xaxis.set(ticks=(0, 1), ticklabels=('Predicted 0s', 'Predicted 1s'))
ax.yaxis.set(ticks=(0, 1), ticklabels=('Actual 0s', 'Actual 1s'))
ax.set_ylim(1.5, -0.5)
for i in range(2):
    for j in range(2):
        ax.text(j, i, cm[i, j], ha='center', va='center', color='red')
plt.show()

model = LogisticRegression(C=10.0, solver = 'liblinear', random_state=0).fit(train_set,train_set_labels)

model.score(train_set,train_set_labels)

0.5768025078369906

prob1 = model.predict_proba(train_set)
predicted=[0 if i>0.54 else 1 for i in prob1[:,0]]
predicted

[0,
 0,
 1,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 1,
 0,
 0,
 1,
 0,
 0,
 1,
 1,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 1,
 0,
 1,
 0,
 1,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 1,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 1,
 0,
 1,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 1,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 1,
 1,
 1,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 1,
 1,
 0,
 1,
 1,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 0,
 0,
 1,
 1,
 0,
 0,
 0,
 1,
 0,
 0,
 0,
 0,
 1]

sum(abs(train_set_labels-predicted))

149

len(train_set_labels)

319

error_percent =sum(abs(train_set_labels-predicted))/319

1-error_percent

0.5329153605015674

from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()

scaled_features = scaler.fit_transform(train_set)

kmeans = KMeans(init="random", n_clusters=5, n_init=10, max_iter=300, random_state=42)

kmeans.fit(scaled_features)

KMeans(init='random', n_clusters=5, random_state=42)

kmeans.inertia_

2974.411076839821

kmeans.cluster_centers_

array([[-7.11156596e-02, -1.43669774e-01, -1.73749959e-01,
        -9.12870929e-02, -1.18004662e-02,  3.50594733e+00,
        -3.33913548e-01, -3.22189740e-01, -3.78641223e-01,
        -2.91605922e-01, -3.39683110e-01, -3.56662979e-01,
        -3.89389970e-01, -3.16227766e-01],
       [-2.90384537e-01,  1.56194832e-01,  1.07580217e-01,
         2.43432248e-01, -1.94930944e-01, -2.85229613e-01,
        -3.33913548e-01,  3.10376116e+00, -3.78641223e-01,
        -2.91605922e-01, -3.39683110e-01, -3.56662979e-01,
        -3.89389970e-01, -3.16227766e-01],
       [ 2.00891778e-01, -1.28259907e-01,  3.47203114e-01,
         2.05717392e-01, -5.20496239e-01, -2.85229613e-01,
        -3.33913548e-01, -3.22189740e-01,  1.02486446e+00,
        -2.91605922e-01, -3.39683110e-01, -3.56662979e-01,
         1.19350246e+00, -3.16227766e-01],
       [ 6.75354560e-02,  1.30370486e-01, -1.24356237e+00,
        -1.09544512e+00,  1.92124347e+00, -2.85229613e-01,
         1.17435697e-01, -3.22189740e-01, -2.03760319e-02,
         2.37238716e-02, -6.14116358e-02,  1.83033261e-02,
        -1.88880849e-01,  3.32307144e-01],
       [-5.79970088e-02,  1.30980991e-03,  3.67861863e-01,
         3.32690739e-01, -5.20496239e-01, -2.85229613e-01,
         2.57855462e-01, -3.22189740e-01, -3.78641223e-01,
         2.59637273e-01,  3.41360558e-01,  3.22244268e-01,
        -3.89389970e-01,  1.47572957e-01]])

kmeans.n_iter_

8

kmeans.labels_[:]

array([4, 4, 3, 3, 4, 2, 3, 4, 4, 2, 4, 4, 2, 2, 4, 0, 0, 4, 3, 4, 4, 2,
       2, 3, 4, 4, 4, 2, 2, 1, 2, 0, 4, 2, 3, 4, 2, 4, 3, 1, 3, 2, 2, 4,
       4, 4, 3, 4, 3, 4, 1, 4, 3, 4, 2, 4, 2, 4, 4, 4, 3, 2, 2, 3, 4, 4,
       0, 0, 4, 4, 2, 4, 4, 4, 4, 3, 2, 2, 4, 2, 1, 4, 3, 2, 4, 3, 2, 4,
       0, 1, 2, 2, 2, 4, 4, 4, 4, 3, 4, 3, 0, 3, 1, 2, 4, 3, 4, 0, 1, 1,
       2, 3, 1, 4, 2, 4, 4, 4, 3, 4, 2, 1, 2, 1, 2, 4, 2, 2, 4, 3, 4, 2,
       1, 4, 4, 4, 3, 2, 1, 0, 2, 3, 2, 2, 4, 2, 4, 0, 4, 3, 2, 4, 2, 4,
       3, 0, 4, 4, 4, 4, 1, 1, 4, 2, 3, 2, 1, 0, 2, 4, 4, 4, 4, 2, 4, 4,
       4, 1, 4, 4, 4, 4, 3, 3, 1, 4, 4, 2, 3, 3, 4, 3, 3, 1, 0, 2, 0, 4,
       3, 1, 2, 4, 2, 4, 4, 2, 2, 3, 2, 3, 0, 2, 4, 4, 3, 3, 1, 4, 4, 4,
       3, 4, 4, 4, 4, 3, 3, 4, 4, 2, 1, 2, 4, 3, 4, 2, 4, 1, 4, 4, 4, 4,
       2, 0, 1, 4, 4, 3, 1, 4, 2, 4, 3, 0, 4, 1, 4, 2, 4, 3, 3, 1, 1, 2,
       0, 0, 3, 4, 4, 3, 4, 4, 4, 2, 3, 1, 2, 4, 2, 4, 4, 4, 4, 4, 4, 3,
       0, 4, 4, 3, 3, 4, 3, 3, 3, 2, 2, 4, 0, 2, 4, 1, 4, 4, 4, 4, 2, 4,
       3, 3, 2, 0, 4, 3, 0, 2, 2, 0, 4])

from sklearn.neighbors import KNeighborsClassifier

model = KNeighborsClassifier(n_neighbors=1)

model.fit(scaled_features,train_set_labels)
predicted = model.predict(scaled_features)
predicted

array([0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1,
       0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0,
       0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0,
       0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1,
       0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0,
       1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1,
       0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1,
       1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1,
       0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
       1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0,
       0, 1, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0,
       0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0,
       1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 0,
       0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1,
       0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0], dtype=int64)

sum(abs(predicted-train_set_labels)) 

0

from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier()
model.fit(train_set, train_set_labels)

RandomForestClassifier()

yhat = model.predict(train_set)

sum(abs(yhat-train_set_labels)) 

0

df1.describe().transpose()

	count	mean	std	min	25%	50%	75%	max
Gender	399.0	5.864662e-01	4.930851e-01	0.000000e+00	0.000000e+00	1.000000e+00	1.000000e+00	1.000000e+00
Children	399.0	1.313283e+00	1.022166e+00	0.000000e+00	0.000000e+00	2.000000e+00	2.000000e+00	3.000000e+00
Salary	399.0	7.894247e+04	2.723687e+04	2.068700e+04	5.812850e+04	7.921200e+04	9.579650e+04	1.601340e+05
Agree or Not	399.0	4.210526e-01	4.943478e-01	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00	1.000000e+00
__Middle-aged	399.0	5.463659e-01	4.984706e-01	0.000000e+00	0.000000e+00	1.000000e+00	1.000000e+00	1.000000e+00
__Young	399.0	2.180451e-01	4.134366e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_California	399.0	8.270677e-02	2.757843e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_Florida	399.0	1.027569e-01	3.040223e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_Illinois	399.0	9.523810e-02	2.939121e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_Michigan	399.0	1.152882e-01	3.197704e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_Minnesota	399.0	7.769424e-02	2.680259e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_New York	399.0	1.152882e-01	3.197704e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_Ohio	399.0	1.102757e-01	3.136263e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_Texas	399.0	1.203008e-01	3.257213e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
State_Virginia	399.0	9.774436e-02	2.973415e-01	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.000000e+00
Gend_child	399.0	8.020050e-01	1.009202e+00	0.000000e+00	0.000000e+00	0.000000e+00	2.000000e+00	3.000000e+00
log_Salary	399.0	1.121107e+01	3.760868e-01	9.937261e+00	1.097039e+01	1.127988e+01	1.146998e+01	1.198377e+01
Salary_Sq	399.0	6.971901e+09	4.626720e+09	4.279520e+08	3.379095e+09	6.274541e+09	9.176971e+09	2.564290e+10

this is where we left off in lecture... additional examples included or we can go through them on another night

from sklearn.neural_network import MLPClassifier

mlp = MLPClassifier(hidden_layer_sizes=(17,13,13,13),max_iter=1000)
mlp.fit(scaled_features,train_set_labels)

MLPClassifier(hidden_layer_sizes=(17, 13, 13, 13), max_iter=1000)

MLPClassifier(activation='relu', alpha=0.0001, batch_size='auto', beta_1=0.9,
       beta_2=0.999, early_stopping=False, epsilon=1e-08,
       hidden_layer_sizes=(17,13,13,13), learning_rate='constant',
       learning_rate_init=0.001, max_iter=1000, momentum=0.9,
       nesterovs_momentum=True, power_t=0.5, random_state=None,
       shuffle=True, solver='adam', tol=0.0001, validation_fraction=0.1,
       verbose=False, warm_start=False)

MLPClassifier(hidden_layer_sizes=(17, 13, 13, 13), max_iter=1000)

predictions = mlp.predict(train_set) #to predict with the test set you'd also have to scale it
predictions

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], dtype=int64)

from sklearn.metrics import classification_report,confusion_matrix
print(confusion_matrix(train_set_labels,predictions)) #this is the same result we got with logistic regression
#experiment with settings to see if you can improve it

[[184   0]
 [135   0]]

print(classification_report(train_set_labels,predictions))

              precision    recall  f1-score   support

           0       0.58      1.00      0.73       184
           1       0.00      0.00      0.00       135

    accuracy                           0.58       319
   macro avg       0.29      0.50      0.37       319
weighted avg       0.33      0.58      0.42       319

C:\Users\Betsy\Anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

import re

txt = "The rain in Spain is mainly on the plain."
x = re.findall("ai", txt)
print(x)

['ai', 'ai', 'ai', 'ai']

x = re.split("\s", txt)
print(x)

['The', 'rain', 'in', 'Spain', 'is', 'mainly', 'on', 'the', 'plain.']

x = re.split("\s", txt, 1) #splits at only the first space
print(x)

['The', 'rain in Spain is mainly on the plain.']

x = re.sub("\s", "-", txt)
print(x)

The-rain-in-Spain-is-mainly-on-the-plain.

x = re.search(r"\bS\w+", txt) #looks for a word with uppercase S at the start, gives start and end position of word
print(x.span())

(12, 17)

print(x.string) #prints whole string where the word appeared

The rain in Spain is mainly on the plain.

print(x.group()) #prints just the word

Spain

x = re.findall("[mat]", txt)
print(x)

['a', 'a', 'm', 'a', 't', 'a']

x = re.findall("ain+", txt)
print(x)

['ain', 'ain', 'ain', 'ain']

#https://www.w3schools.com/python/python_regex.asp more code keys here